CN106446552A - Prediction method and prediction system for sleep disorder based on incremental neural network model - Google Patents
Prediction method and prediction system for sleep disorder based on incremental neural network model Download PDFInfo
- Publication number
- CN106446552A CN106446552A CN201610860347.2A CN201610860347A CN106446552A CN 106446552 A CN106446552 A CN 106446552A CN 201610860347 A CN201610860347 A CN 201610860347A CN 106446552 A CN106446552 A CN 106446552A
- Authority
- CN
- China
- Prior art keywords
- sleep disorder
- neuron
- network model
- neural network
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a prediction method for a sleep disorder based on an incremental neural network model. The method comprises the steps that a database of sleep disorder daily data is established; the neural network model is trained; daily life data is collected and sent to a server; data of the present day is extracted from a user daily data recording list, and a n-dimensional vector is formed, normalized and input into a pathologic neural network model of the sleep disorder, so that the danger degree and probability of the sleep disorder can be predicted; intelligent home-use sleep disorder nursing equipment judges whether the danger degree W of the sleep disorder is larger than or equal to 3; when a user receives a warning from a warning indicator, the user can go to a hospital for examination and transmit examination results to a server, and the server judges whether the examination results are correct; and an incremental algorithm will be executed when the examination results are wrong, and then the neural network model will be modified dynamically. According to the invention, prediction is accurate, and a neural network model can be customized for each user.
Description
Technical field
The invention belongs to field of medical technology, more particularly to a kind of sleep disorder based on increment type neural network model
Forecasting Methodology and prognoses system.
Background technology
Current domestic each health management system arranged be respectively provided with sleep disorder prediction and evaluation, the prediction mode which uses be
Join.Its principle is that by system matches fixed data and then personal lifestyle data entry system is shown ill probability.But due to people
The complexity, unpredictability of body and disease, in the form of expression of the bio signal with information, Changing Pattern (Self-variation with
Change after medical intervention) on, which being detected and signal representation, the data of acquisition and the analysis of information, decision-making etc. are all multi-party
All there is extremely complex non-linear relationship in face.So can only be the data examination of blindness using traditional Data Matching, it is impossible to
Judge the logic association between data and data and variable, the codomain deviation for obtaining is big, causes the specificity ten of system prediction
It is poor to divide, so the current country is health management system arranged effectively cannot carry out Accurate Prediction to personal sleep disorder.
Most of before this to sleep disorder prediction be all using BP neural network model, but when new detection data is produced
When, it is necessary to train neural network model again, operation efficiency is extremely low.And after system user scale increases, service
Device will be unable to complete training mission in time.
Content of the invention
The purpose of the present invention is that and overcomes the deficiencies in the prior art, there is provided a kind of based on increment type neural network model
Sleep disorder Forecasting Methodology and prognoses system, the present invention is by the neural network model training a large amount of patient in hospital pathology numbers of prediction
According to finding sleep disorder pathology and sleep disorder earlier life variations in detail, clinical symptoms, examination criteria value, high-risk group spy
Levy, the logic association between this several causes of disease and variable, ultimately form the sleep barrier to sleep disorder illness probability Accurate Prediction
Hinder pathology neural network model, the present invention is by gathering user's daily life data, the periodicity of its data of active analysis, rule
Property suffers from sleep disorder probability eventually through sleep disorder pathology Neural Network model predictive user, is carried in the way of visual effect
Awake user's instant hospitalizing, constantly revises neural network model when Neural Network model predictive is inaccurate by increasable algorithm,
To set up, for each equipment user, the neural network model for training for the user, with the increase of use time, to build
The vertical neural network model made to measure by the user, accuracy rate is greatly improved.
To achieve these goals, the invention provides a kind of sleep disorder based on increment type neural network model is predicted
Method, comprises the steps：
Step (1), acquisition hospital's sleep disorder etiology and pathology data source and the daily monitoring data of patient, so as to set up sleep
The daily data database of obstacle；
Step (2), the daily data database of the sleep disorder that is set up according to step (1) are off-line manner to neutral net
Model is trained, with the sleep disorder pathology neural network model for obtaining training；
Step (3), by intelligent monitoring device, the daily life data of user are acquired, and will collection daily life
Live data is sent to server, during server preserves the daily life data of user to the daily data logger of user；
Step (4), from the daily data logger of user, same day data are extracted, n-dimensional vector is formed, and n-dimensional vector is done
Sleep disorder danger journey is carried out in the sleep disorder pathology neural network model for training in input step (2) after normalized
Degree probabilistic forecasting, obtains sleep disorder probability results array P, and corresponding for maximum probability in array P sleep disorder is endangered by server
Dangerous degree value W sends wired home sleep disorder care appliances to；
Step (5), sleep disorder degree of danger value W of wired home sleep disorder care appliances the reception server transmission
Afterwards, whether sleep disorder degree of danger value W is judged more than or equal to 3, if greater than being equal to 3, then attention device is warned to remind user,
If less than 3, then attention device is not warned；
Step (6), when user receive attention device warning when, user voluntarily removes examination in hospital, and inspection result is passed through
Wired home sleep disorder care appliances send back server, and server judges whether inspection result is correct, if inspection result
Mistake, then explanation sleep disorder pathology Neural Network model predictive is inaccurate, if inspection result is correct, sleep disorder is described
Pathology Neural Network model predictive is accurate；
Step (7), when inspection result mistake, from the daily data logger of user extract m days in record preserve to
In incremental data table, when the record quantity in incremental data table is more than h bar, increasable algorithm is executed, to sleep disorder pathology
Neural network model carries out dynamic corrections；
Step (8), repeat step (3)～(7).
Further, the input layer of neural network model is n node, and hidden layer number is that n*2+1, output layer is 1
Node, extracts k bar record from the daily data database table of sleep disorder and is trained, and per bar, record is a n-dimensional vector, institute
There are data using front elder generation through normalized so as to which then numerical value execute following steps to neutral net mould in [0,1] interval
Type is trained：
1) n-dimensional vector being input into neural network model, calculates all of weight vector in neural network model defeated to this
Enter the distance of n-dimensional vector, closest neuron is triumph neuron, and its computing formula is as follows：
Wherein：WkIt is the weight vector of triumph neuron, | | ... | | for Euclidean distance；
2) weight vector of the neuron in adjustment triumph neuron and triumph neuron field, formula is as follows：
Wherein：WjT () is neuron；Wj(t+1) weight vector before being adjustment and after adjustment；J belongs to triumph neuron neck
Domain；α (t) is learning rate, and it is the function for gradually successively decreasing with the increase of iterationses, and span is [0 1], through multiple
It is 0.71 that Optimal learning efficiency is chosen in experiment；DjIt is the distance of neuron j and triumph neuron；σ (t) is the letter for successively decreasing over time
Number；Iteration is all input to all input n-dimensional vectors in neural network model and is trained each time, when the iteration for reaching regulation
After number of times, neural network model training terminates.
Further, inspection result is sent back wired home sleep disorder care appliances the lattice of the object information of server
Formula is：{ the sleep disorder degree of danger value of the actual judgement of doctor }, server judges inspection result after object information is received
Whether correct.
Further, the increasable algorithm for carrying out dynamic corrections to sleep disorder pathology neural network model is：
In incremental data table per bar vector V { V1,V2,…,Vn, it is sent in neural network model learning function
Row study, learning procedure is as follows：
1) first little random number is assigned to each weight vector of output layer and normalized is done, then using input mode vector V
Meansigma methodss Avg (V), be initialized as the weights of unique neuron in the 0th layer of neural network model, and be set to nerve of winning
Unit, calculates its quantization error QE；
2) 2 × 2 structures SOM are expanded out from the 0th layer of neuron, and its level identities Layer is set to 1；
3) for each 2 × 2 structure SOM subnet that expands out in Layer layer, the power of this 4 neurons is initialized
Value；The input vector set Ci of i-th neuron is set to sky, main label is set to the main label ratio r of NULL, neuron ii
It is set to 0；The abnormity early warning data vector V of new SOM inherits the triumph input vector set VX of his father's neuron；
4) a vector VX is selected from VXiDo following judgement：
If VXiFor the data of not tape label, then its Euclidean distance with each neuron is calculated, chosen distance is most short
Neuron is used as triumph neuron；
If VXiFor the data of tape label, then select main label and VXiThe identical and r of labeliThe maximum neuron of value is made
For triumph neuron, the triumph neuron main label is updated；
If can not find main label with VXiLabel identical neuron, then find and VXiClosest neuron i makees
For triumph neuron；
5) weights of neuron in triumph neuron and its neighborhood are adjusted, update the vector set W=W ∪ that wins
{VXi, calculate main label, the main label ratio r of triumph neuroniWith comentropy EiIf. not up to predetermined frequency of training,
Go to step 4)；
6) quantization error QE of each neuron in the neural network model after calculating is adjustedi, neuronal messages entropy Ei
With the average quantization error MQE of subnet, formula is as follows：
Wherein：WiFor the weight vector of neuron i, CiFor the set that all input vectors for being mapped to neuron i are constituted；
Wherein：niRepresent to fall that label is the number of samples of i on neuron, m represents to fall label data on neuron
Sum, T represents to fall the sample label species set on neuron；
Then judge：
If MQE>QE × threshold value q of father node, wherein q=0.71, then insert a line neuron in the SOM, turn step
Rapid 4)；
If Ei>The E of father nodei× threshold value p, wherein p=0.42, then grow one layer of new subnet from the neuron, will
The subnet for newly growing increases in the subnet queue of Layer+1 layer；
If new neuron is not inserted in SOM also do not grow new subnet, illustrate that the subnet training is completed；
7) for all 2 × 2 structures SOM of the Layer+1 layer that newly expands out, iteration operating procedure 3)～5) to which again
It is trained, until neural network model no longer produces new neuron and new layering, whole training terminates.
Further, in step (4), sleep disorder probability results array P for obtaining is one 6 dimension variable, and its 6 dimension becomes
Amount is respectively 6 sleep disorder degree of danger probability, the corresponding sleep of maximum probability in 6 sleep disorder degree of danger probability
Obstacle degree of danger value W sends wired home sleep disorder care appliances to；In step (5), when sleep disorder degree of danger
Represent preferable during value W=1, represent normal during W=2, during W=3, represent subhealth state, represent dangerous during W=4, represent during W=5 non-
Often dangerous, represent ill during W=6.
Further, if user includes health check-up by other means and checks oneself, learn and sleep disorder oneself is had suffered from, and intelligence
The attention device of energy domestic sleeping obstacle care appliances is not warned, then it represents that wired home sleep disorder care appliances judge inaccurate
Really, now execution step (6)～(7), wired home sleep disorder care appliances are sent to object information on server.
Present invention also offers a kind of prognoses system of the sleep disorder Forecasting Methodology, including intelligent monitoring device, intelligence
Energy device data acquisition device, server and wired home sleep disorder care appliances, the intelligent monitoring device and the intelligence
Device data acquisition device is connected, and the smart machine data acquisition unit is logical with the server network by communication device one
News, the wired home sleep disorder care appliances are communicated with the server network by communication device two.
Further, on the wired home sleep disorder care appliances, attention device is provided with.
Further, the intelligent monitoring device include Intelligent worn device, Intelligent water cup, Intelligent weight claim, intelligent horse
Bucket and Intelligent light sensing equipment.
Beneficial effects of the present invention：
1st, the present invention finds sleep disorder pathology by a large amount of patient in hospital pathological data of neural network model training prediction
With sleep disorder earlier life variations in detail, clinical symptoms, examination criteria value, high-risk group's feature, between this several causes of disease
Logic association and variable, ultimately form the sleep disorder pathology neural network model to sleep disorder illness probability Accurate Prediction,
The present invention is by gathering user's daily life data, and the periodicity of its data of active analysis, regularity are eventually through sleep disorder
Pathology Neural Network model predictive user suffers from sleep disorder degree of danger probability, reminds user instant in the way of visual effect
Seek medical advice and prevent.
2nd, when Neural Network model predictive is inaccurate, neural network model is constantly revised by increasable algorithm, to be directed to
Each equipment user sets up the neural network model for training for the user, with the increase of use time, to set up to this
The neural network model that user makes to measure, accuracy rate is greatly improved.
Description of the drawings
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
Accompanying drawing to be used needed for technology description is had to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, acceptable
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the flow chart of the embodiment of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawings invention is further illustrated, but be not limited to the scope of the present invention.
Embodiment
As shown in figure 1, a kind of sleep disorder Forecasting Methodology based on increment type neural network model that the present invention is provided, bag
Include following steps：
Step (1), acquisition hospital's sleep disorder etiology and pathology data source and the daily monitoring data of patient, so as to set up sleep
The daily data database of obstacle；
Wherein daily monitoring data is 21 item data, and its 21 item data is age, sex, and heart rate sleeps front excitatory state, in vain
Its emotional status, sleep quality, snoring (daily), the amount of drinking (daily), the amount of drinking water and frequency, work fatigue degree, body aches
Pain state, night sleeping position, the length of one's sleep, deep sleep's time, Sleeps hyperhidrosis, body temperature, pursue an occupation, the length of one's sleep and quality,
21 item data such as travel distance (daily), the present invention sets up 21 dimensional vectors with 21 item data；
Step (2), the daily data database of the sleep disorder that is set up according to step (1) are off-line manner to neutral net
Model is trained, with the sleep disorder pathology neural network model for obtaining training；
Step (3), by intelligent monitoring device, the daily life data of user are acquired, and will collection daily life
Live data is sent to server, during server preserves the daily life data of user to the daily data logger of user；
Step (4), from the daily data logger of user, same day data are extracted, n-dimensional vector is formed, and n-dimensional vector is done
Sleep disorder danger journey is carried out in the sleep disorder pathology neural network model for training in input step (2) after normalized
Degree probabilistic forecasting, obtains sleep disorder probability results array P, and corresponding for maximum probability in array P sleep disorder is endangered by server
Dangerous degree value W sends wired home sleep disorder care appliances to；
Wherein in step (4), sleep disorder probability results array P for obtaining is one 6 dimension variable, and its 6 dimension variable divides
Not Wei 6 sleep disorder degree of danger probability, the corresponding sleep disorder of maximum probability in 6 sleep disorder degree of danger probability
Degree of danger value W sends wired home sleep disorder care appliances to.
Step (5), sleep disorder degree of danger value W of wired home sleep disorder care appliances the reception server transmission
Afterwards, whether sleep disorder degree of danger value W is judged more than or equal to 3, if greater than being equal to 3, then attention device is warned to remind user,
If less than 3, then attention device is not warned；
Wherein in step (5), represent preferable when sleep disorder degree of danger value W=1, during W=2, represent normal, W=
Represent subhealth state when 3, represent dangerous during W=4, during W=5, represent abnormally dangerous, during W=6, represent ill.I.e. the present invention will sleep
Obstacle degree of danger is divided into 6 grades, more accurate and visual.
Step (6), when user receive attention device warning when, user voluntarily removes examination in hospital, and inspection result is passed through
Wired home sleep disorder care appliances send back server, and server judges whether inspection result is correct, if inspection result
Mistake, then explanation sleep disorder pathology Neural Network model predictive is inaccurate, if inspection result is correct, sleep disorder is described
Pathology Neural Network model predictive is accurate；
The form that wherein inspection result is sent back wired home sleep disorder care appliances the object information of server is：
{ the sleep disorder degree of danger value of the actual judgement of doctor }, whether server judges inspection result after object information is received
Correctly.
Step (7), when inspection result mistake, from the daily data logger of user extract 7 days in record preserve to
In incremental data table, when the record quantity in incremental data table is more than 100, increasable algorithm is executed, to sleep disorder disease
Reason neural network model carries out dynamic corrections；
Step (8), repeat step (3)～(7).
The input layer of the neural network model of the present invention is 21 nodes, and it is 6 nodes that hidden layer number is 43, output layer
(i.e. 6 sleep disorder degree of danger probability), extracting 400000 records from the daily data database table of sleep disorder is carried out
Training, per bar, record is 21 dimensional vectors, and all data are using front elder generation through normalized so as to which numerical value is in [0,1] area
Between, then execute following steps and neural network model is trained：
1) 21 dimensional vectors are input into neural network model, calculate all of weight vector in neural network model defeated to this
Enter the distance of 21 dimensional vectors, closest neuron is triumph neuron, and its computing formula is as follows：
Wherein：WkIt is the weight vector of triumph neuron, | | ... | | for Euclidean distance；
2) weight vector of the neuron in adjustment triumph neuron and triumph neuron field, formula is as follows：
Wherein：WjT () is neuron；Wj(t+1) weight vector before being adjustment and after adjustment；J belongs to triumph neuron neck
Domain；α (t) is learning rate, and it is the function for gradually successively decreasing with the increase of iterationses, and span is [0 1], through multiple
It is 0.71 that Optimal learning efficiency is chosen in experiment；DjIt is the distance of neuron j and triumph neuron；σ (t) is the letter for successively decreasing over time
Number；Iteration is all input to all input n-dimensional vectors in neural network model and is trained each time, when the iteration for reaching regulation
After number of times, neural network model training terminates.
The increasable algorithm for dynamic corrections being carried out to sleep disorder pathology neural network model of the present invention is：
In incremental data table per bar vector V { V1,V2,…,Vn, it is sent in neural network model learning function
Row study, learning procedure is as follows：
1) first little random number is assigned to each weight vector of output layer and normalized is done, then using input mode vector V
Meansigma methodss Avg (V), be initialized as the weights of unique neuron in the 0th layer of neural network model, and be set to nerve of winning
Unit, calculates its quantization error QE；
2) 2 × 2 structures SOM are expanded out from the 0th layer of neuron, and its level identities Layer is set to 1；
3) for each 2 × 2 structure SOM subnet that expands out in Layer layer, the power of this 4 neurons is initialized
Value；The input vector set Ci of i-th neuron is set to sky, main label is set to the main label ratio r of NULL, neuron ii
It is set to 0；The abnormity early warning data vector V of new SOM inherits the triumph input vector set VX of his father's neuron；
4) a vector VX is selected from VXiDo following judgement：
If VXiFor the data of not tape label, then its Euclidean distance with each neuron is calculated, chosen distance is most short
Neuron is used as triumph neuron；
If VXiFor the data of tape label, then select main label and VXiThe identical and r of labeliThe maximum neuron of value is made
For triumph neuron, the triumph neuron main label is updated；
If can not find main label with VXiLabel identical neuron, then find and VXiClosest neuron i makees
For triumph neuron；
5) weights of neuron in triumph neuron and its neighborhood are adjusted, update the vector set W=W ∪ that wins
{VXi, calculate main label, the main label ratio r of triumph neuroniWith comentropy EiIf. not up to predetermined frequency of training,
Go to step 4)；
6) quantization error QE of each neuron in the neural network model after calculating is adjustedi, neuronal messages entropy Ei
With the average quantization error MQE of subnet, formula is as follows：
Wherein：WiFor the weight vector of neuron i, CiFor the set that all input vectors for being mapped to neuron i are constituted；
Wherein：niRepresent to fall that label is the number of samples of i on neuron, m represents to fall label data on neuron
Sum, T represents to fall the sample label species set on neuron；
Then judge：
If MQE>QE × threshold value q of father node, wherein q=0.71, then insert a line neuron in the SOM, turn step
Rapid 4)；
If Ei>The E of father nodei× threshold value p, wherein p=0.42, then grow one layer of new subnet from the neuron, will
The subnet for newly growing increases in the subnet queue of Layer+1 layer；
If new neuron is not inserted in SOM also do not grow new subnet, illustrate that the subnet training is completed；
7) for all 2 × 2 structures SOM of the Layer+1 layer that newly expands out, iteration operating procedure 3)～5) to which again
It is trained, until neural network model no longer produces new neuron and new layering, whole training terminates.
If user includes health check-up by other means and checks oneself, learn and sleep disorder oneself is had suffered from, and wired home is slept
The attention device of dormancy obstacle care appliances is not warned, then it represents that wired home sleep disorder care appliances judge inaccurate, now
Execution step (6)～(7), wired home sleep disorder care appliances are sent to object information on server.
Present invention also offers a kind of prognoses system of the sleep disorder Forecasting Methodology, including intelligent monitoring device, intelligence
Energy device data acquisition device, server and wired home sleep disorder care appliances, the intelligent monitoring device and the intelligence
Device data acquisition device is connected, and the smart machine data acquisition unit is logical with the server network by communication device one
News, the wired home sleep disorder care appliances are communicated with the server network by communication device two.
Attention device is provided with the wired home sleep disorder care appliances of the present invention.
The intelligent monitoring device of the present invention include Intelligent worn device, Intelligent water cup, Intelligent weight claim, intelligent closestool
With Intelligent light sensing equipment etc..
The present invention by the neural network model training a large amount of patient in hospital pathological data of prediction, find sleep disorder pathology with
Sleep disorder earlier life variations in detail, clinical symptoms, examination criteria value, high-risk group's feature, patrolling between this several causes of disease
Association and variable is collected, the sleep disorder pathology neural network model to sleep disorder illness probability Accurate Prediction is ultimately formed, this
Invention is by gathering user's daily life data, and the periodicity of its data of active analysis, regularity are eventually through sleep disorder disease
Reason Neural Network model predictive user suffers from sleep disorder probability, reminds user's instant hospitalizing and pre- in the way of visual effect
Anti-.
During all data of the present invention are preserved to server, calculating cost can be significantly saved, hardware configuration is low, so as to sell
Valency is also low.
The present invention carries communication device one and communication device two, can pass through wifi from the Internet that is dynamically connected, and protect for a long time
Hold online.Various intelligent monitoring devices can easily access present device by modes such as network or bluetooths, set in acquisition
The daily life data of the monitoring of intelligent monitoring device, data that therefore present device obtain are uploaded automatically after standby mandate can
It is real-time, accurate, polynary.
As everyone physical trait is different, the data characteristicses for being shown during sleep disorder morbidity also can be different.
Therefore conventional not high by the method accuracy rate of neural network prediction sleep disorder.The present invention is set up for each equipment user
The neural network model for the user is trained, in operation after a period of time, by producing to measure nerve is made to the user
Network Prediction Model, accuracy rate is greatly improved.
When neural network model is judged by accident, error message will be feedbacked to service by wired home sleep disorder care appliances
Device, for user's dynamic corrections neural network model, when similar characteristics data occurs in the next user, will not be missed again
Sentence.Therefore, with the increase of use time, the judgement of the wired home sleep disorder care appliances of the present invention will be more and more accurate
Really.
Ultimate principle, principal character and the advantages of the present invention of the present invention has been shown and described above.The technology of the industry
Personnel it should be appreciated that the present invention is not restricted to the described embodiments, simply explanation described in above-described embodiment and description this
The principle of invention, without departing from the spirit and scope of the present invention the present invention also have various changes and modifications, these change
Change and improvement is both fallen within scope of the claimed invention.The claimed scope of the invention by appending claims and its
Equivalent is defined.
Claims (9)
1. a kind of sleep disorder Forecasting Methodology based on increment type neural network model, it is characterised in that comprise the steps：
Step (1), obtain hospital sleep disorder and cure the disease etiology and pathology data source and the daily monitoring data of patient, so as to set up sleep
The daily data database of obstacle；
Step (2), the daily data database of the sleep disorder that is set up according to step (1) are off-line manner to neural network model
It is trained, with the sleep disorder pathology neural network model for obtaining training；
Step (3), by intelligent monitoring device, the daily life data of user are acquired, and will collection daily life number
According to transmission to server, during server preserves the daily life data of user to the daily data logger of user；
Step (4), from the daily data logger of user, same day data are extracted, n-dimensional vector is formed, and normalizing is done to n-dimensional vector
Sleep disorder degree of danger is carried out in the sleep disorder pathology neural network model for training in input step (2) after change process general
Rate predict, obtain sleep disorder probability results array P, server by corresponding for maximum probability in array P sleep disorder danger journey
Angle value W sends wired home sleep disorder care appliances to；
After step (5), sleep disorder degree of danger value W of wired home sleep disorder care appliances the reception server transmission, sentence
Whether disconnected sleep disorder degree of danger value W is more than or equal to 3, and if greater than being equal to 3, then attention device is warned to remind user, if
Less than 3, then attention device is not warned；
Step (6), when user receives attention device warning, user voluntarily removes examination in hospital, and by inspection result by intelligence
Domestic sleeping obstacle care appliances send back server, and server judges whether inspection result is correct, if inspection result mistake,
Then explanation sleep disorder pathology Neural Network model predictive is inaccurate, if inspection result is correct, sleep disorder pathology is described
Neural Network model predictive is accurate；
Step (7), when inspection result mistake, from the daily data logger of user extract m days in record preserve to increment
In tables of data, when the record quantity in incremental data table is more than h bar, increasable algorithm is executed, to sleep disorder pathology nerve
Network model carries out dynamic corrections；
Step (8), repeat step (3)～(7).
2. a kind of sleep disorder Forecasting Methodology based on increment type neural network model according to claim 1, its feature
It is, the input layer of neural network model is n node, and it is 1 node that hidden layer number is n*2+1, output layer, from sleep barrier
Extraction k bar record in daily data database table is hindered to be trained, record is a n-dimensional vector per bar, and all data are being used
Front elder generation is through normalized so as to which then numerical value is executed following steps and neural network model is trained in [0,1] interval：
1) n-dimensional vector being input into neural network model, calculates all of weight vector in neural network model and tie up to input n
The distance of vector, closest neuron is triumph neuron, and its computing formula is as follows：
Wherein：WkIt is the weight vector of triumph neuron, | | ... | | for Euclidean distance；
2) weight vector of the neuron in adjustment triumph neuron and triumph neuron field, formula is as follows：
Wherein：WjT () is neuron；Wj(t+1) weight vector before being adjustment and after adjustment；J belongs to triumph neuron field；α
T () is learning rate, it is the function for gradually successively decreasing with the increase of iterationses, and span is [0 1], through many experiments
It is 0.71 to choose Optimal learning efficiency；DjIt is the distance of neuron j and triumph neuron；σ (t) is the function for successively decreasing over time；
Iteration is all input to all input n-dimensional vectors in neural network model and is trained each time, when the iteration time for reaching regulation
After number, neural network model training terminates.
3. a kind of sleep disorder Forecasting Methodology based on increment type neural network model according to claim 1, its feature
It is, the form of the object information that inspection result is sent back wired home sleep disorder care appliances server is：{ doctor's reality
The sleep disorder degree of danger value that border judges }, server judges whether inspection result is correct after object information is received.
4. a kind of sleep disorder Forecasting Methodology based on increment type neural network model according to claim 1, its feature
It is, the increasable algorithm for carrying out dynamic corrections to sleep disorder pathology neural network model is：
In incremental data table per bar vector V { V1,V2,…,Vn, it is sent in neural network model learning function and is learned
Practise, learning procedure is as follows：
1) first little random number is assigned to each weight vector of output layer and normalized is done, then using the flat of input mode vector V
Average Avg (V), is initialized as the weights of unique neuron in the 0th layer of neural network model, and is set to triumph neuron, meter
Calculate its quantization error QE；
2) 2 × 2 structures SOM are expanded out from the 0th layer of neuron, and its level identities Layer is set to 1；
3) for each 2 × 2 structure SOM subnet that expands out in Layer layer, the weights of this 4 neurons are initialized；Will
The input vector set Ci of i-th neuron is set to sky, and main label is set to the main label ratio r of NULL, neuron iiIt is set to
0；The abnormity early warning data vector V of new SOM inherits the triumph input vector set VX of his father's neuron；
4) a vector VX is selected from VXiDo following judgement：
If VXiFor the data of not tape label, then calculate its Euclidean distance with each neuron, the most short nerve of chosen distance
Unit is used as triumph neuron；
If VXiFor the data of tape label, then select main label and VXiThe identical and r of labeliThe neuron of value maximum is used as obtaining
Victory neuron, updates the triumph neuron main label；
If can not find main label with VXiLabel identical neuron, then find and VXiClosest neuron i is used as obtaining
Victory neuron；
5) weights of neuron in triumph neuron and its neighborhood are adjusted, update the vector set W=W ∪ { VX that winsi,
Calculate main label, the main label ratio r of triumph neuroniWith comentropy EiIf. not up to predetermined frequency of training, go to step
4)；
6) quantization error QE of each neuron in the neural network model after calculating is adjustedi, neuronal messages entropy EiAnd son
The average quantization error MQE of net, formula is as follows：
Wherein：WiFor the weight vector of neuron i, CiFor the set that all input vectors for being mapped to neuron i are constituted；
Wherein：niRepresent to fall that label is the number of samples of i on neuron, m represents to fall the total of label data on neuron
Number, T represents to fall the sample label species set on neuron；
Then judge：
If MQE>QE × threshold value q of father node, wherein q=0.71, then insert a line neuron in the SOM, go to step 4)；
If Ei>The E of father nodei× threshold value p, wherein p=0.42, then grow one layer of new subnet from the neuron, will be new
The subnet for growing increases in the subnet queue of Layer+1 layer；
If new neuron is not inserted in SOM also do not grow new subnet, illustrate that the subnet training is completed；
7) for all 2 × 2 structures SOM of the Layer+1 layer that newly expands out, iteration operating procedure 3)～5) which is re-started
Training, until neural network model no longer produces new neuron and new layering, whole training terminates.
5. a kind of sleep disorder Forecasting Methodology based on increment type neural network model according to claim 1, its feature
It is, in step (4), sleep disorder probability results array P for obtaining is one 6 dimension variable, and its 6 dimension variable is respectively 6
Sleep disorder degree of danger probability, corresponding for maximum probability in 6 sleep disorder degree of danger probability sleep disorder danger journey
Angle value W sends wired home sleep disorder care appliances to；In step (5), the table when sleep disorder degree of danger value W=1
Show ideal, during W=2, represent normal, during W=3, represent subhealth state, represent dangerous during W=4, during W=5, represent abnormally dangerous, W=6
When represent ill.
6. a kind of sleep disorder Forecasting Methodology based on increment type neural network model according to claim 1, its feature
It is, if user includes health check-up by other means and checks oneself, learns and sleep disorder oneself is had suffered from, and wired home sleep barrier
The attention device of care appliances is hindered not warn, then it represents that wired home sleep disorder care appliances judge inaccurate, now execute
Step (6)～(7), wired home sleep disorder care appliances are sent to object information on server.
7. the prognoses system of sleep disorder Forecasting Methodology described in a kind of employing claim 1～7, it is characterised in that including intelligence
Monitoring device, smart machine data acquisition unit, server and wired home sleep disorder care appliances, the intelligent monitoring device
It is connected with the smart machine data acquisition unit, the smart machine data acquisition unit is by communication device one and the service
Device network communication, the wired home sleep disorder care appliances are communicated with the server network by communication device two.
8. the prognoses system of sleep disorder Forecasting Methodology according to claim 8, it is characterised in that the wired home sleep
Attention device is provided with obstacle care appliances.
9. the prognoses system of sleep disorder Forecasting Methodology according to claim 8, it is characterised in that the intelligent monitoring device
Claim including Intelligent worn device, Intelligent water cup, Intelligent weight, intelligent closestool and Intelligent light sensing equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610860347.2A CN106446552A (en) | 2016-09-28 | 2016-09-28 | Prediction method and prediction system for sleep disorder based on incremental neural network model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610860347.2A CN106446552A (en) | 2016-09-28 | 2016-09-28 | Prediction method and prediction system for sleep disorder based on incremental neural network model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106446552A true CN106446552A (en) | 2017-02-22 |
Family
ID=58170728
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610860347.2A Pending CN106446552A (en) | 2016-09-28 | 2016-09-28 | Prediction method and prediction system for sleep disorder based on incremental neural network model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106446552A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108310587A (en) * | 2018-02-02 | 2018-07-24 | 贺鹏程 | A kind of sleep control device and method |
| CN110824944A (en) * | 2019-11-22 | 2020-02-21 | 珠海格力电器股份有限公司 | Sleep behavior information prediction method and system based on intelligent household equipment |
| CN111166286A (en) * | 2020-01-03 | 2020-05-19 | 珠海格力电器股份有限公司 | Dreamy travel detection method, storage medium and dreamy travel detection device |
| CN112668415A (en) * | 2020-12-17 | 2021-04-16 | 震兑工业智能科技有限公司 | Aircraft engine fault prediction method |
| WO2022057057A1 (en) * | 2020-09-15 | 2022-03-24 | 深圳大学 | Method for detecting medicare fraud, and system and storage medium |
| CN118197557A (en) * | 2024-05-16 | 2024-06-14 | 深圳市金大智能创新科技有限公司 | AI-based neural analysis method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1477581A (en) * | 2003-07-01 | 2004-02-25 | �Ϻ���ͨ��ѧ | Predictive modelling method application to computer-aided medical diagnosis |
| CN102647292A (en) * | 2012-03-20 | 2012-08-22 | 北京大学 | Intrusion detecting method based on semi-supervised neural network |
| CN105118010A (en) * | 2015-09-30 | 2015-12-02 | 成都信汇聚源科技有限公司 | Chronic disease management method with functions of real-time data processing and real-time information sharing and life style intervention information |
-
2016
- 2016-09-28 CN CN201610860347.2A patent/CN106446552A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1477581A (en) * | 2003-07-01 | 2004-02-25 | �Ϻ���ͨ��ѧ | Predictive modelling method application to computer-aided medical diagnosis |
| CN102647292A (en) * | 2012-03-20 | 2012-08-22 | 北京大学 | Intrusion detecting method based on semi-supervised neural network |
| CN105118010A (en) * | 2015-09-30 | 2015-12-02 | 成都信汇聚源科技有限公司 | Chronic disease management method with functions of real-time data processing and real-time information sharing and life style intervention information |
Non-Patent Citations (2)
| Title |
|---|
| MATLAB中文论坛: "《MATLAB 神经网络30个案例分析》", 30 April 2010, 北京航空航天大学出版社 * |
| 王晓海 吴志刚 译: "《数据挖掘：概念、模型、方法和算法》", 31 January 2013, 清华大学出版社 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108310587A (en) * | 2018-02-02 | 2018-07-24 | 贺鹏程 | A kind of sleep control device and method |
| CN108310587B (en) * | 2018-02-02 | 2021-03-16 | 贺鹏程 | Sleep control device and method |
| CN110824944A (en) * | 2019-11-22 | 2020-02-21 | 珠海格力电器股份有限公司 | Sleep behavior information prediction method and system based on intelligent household equipment |
| CN111166286A (en) * | 2020-01-03 | 2020-05-19 | 珠海格力电器股份有限公司 | Dreamy travel detection method, storage medium and dreamy travel detection device |
| WO2022057057A1 (en) * | 2020-09-15 | 2022-03-24 | 深圳大学 | Method for detecting medicare fraud, and system and storage medium |
| CN112668415A (en) * | 2020-12-17 | 2021-04-16 | 震兑工业智能科技有限公司 | Aircraft engine fault prediction method |
| CN118197557A (en) * | 2024-05-16 | 2024-06-14 | 深圳市金大智能创新科技有限公司 | AI-based neural analysis method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106446552A (en) | Prediction method and prediction system for sleep disorder based on incremental neural network model | |
| CN106407699A (en) | Coronary heart disease prediction method and prediction system based on incremental neural network model | |
| CN106250712A (en) | A kind of ureteral calculus Forecasting Methodology based on increment type neural network model and prognoses system | |
| CN106446560A (en) | Hyperlipidemia prediction method and prediction system based on incremental neural network model | |
| CN106355035A (en) | Pneumonia prediction method and prediction system based on incremental neural network model | |
| CN106650206A (en) | Prediction method of high blood pressure based on incremental neural network model and prediction system | |
| CN106384013A (en) | Incremental neural network model-based type-II diabetes prediction method and prediction system | |
| CN111081379A (en) | Disease probability decision method and system | |
| CN113241196A (en) | Remote medical treatment and grading monitoring system based on cloud-terminal cooperation | |
| CN106384005A (en) | Incremental neural network model-based depression prediction method and prediction system | |
| CN106295238A (en) | A kind of hypertensive nephropathy Forecasting Methodology based on increment type neural network model and prognoses system | |
| CN106355034A (en) | Sub-health prediction method and prediction system based on incremental neural network model | |
| CN106384012A (en) | Incremental neural network model-based allergic dermatitis prediction method and prediction system | |
| CN106384008A (en) | Incremental neural network model-based allergic rhinitis prediction method and prediction system | |
| CN106407694A (en) | Neurasthenia prediction method and prediction system based on incremental neural network model | |
| CN106407693A (en) | Hepatitis B prediction method and prediction system based on incremental neural network model | |
| CN106202986A (en) | A kind of tonsillitis Forecasting Methodology based on increment type neural network model and prognoses system | |
| CN106250715A (en) | A kind of chronic pharyngolaryngitis Forecasting Methodology based on increment type neural network model and prognoses system | |
| CN106446561A (en) | Incremental neural network model based urticaria prediction method and system | |
| CN106384009A (en) | Incremental neural network model-based HIV prediction method and prediction system | |
| CN106446550A (en) | Cold prediction method and system based on incremental neutral network model | |
| CN106407695A (en) | Anxiety disorder prediction method and prediction system based on incremental neural network model | |
| CN106446563A (en) | Incremental neural network model based constipation prediction method and system | |
| CN106295239A (en) | A kind of fatty liver Forecasting Methodology based on increment type neural network model and prognoses system | |
| CN106250714A (en) | A kind of renal calculus Forecasting Methodology based on increment type neural network model and prognoses system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170222 |